Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4358. Min Range: -2.4358

Max Act: 2.4358. Min Act: -0.0000

Data Index: 443840 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 2.4358. Min Range: -2.4358

Max Act: 2.1253. Min Act: -0.0001

Data Index: 895528 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1028039 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.4358. Min Range: -2.4358

Max Act: 2.0796. Min Act: -0.0001

Data Index: 56712 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.9372. Min Act: -0.0001

Data Index: 933477 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.9234. Min Act: -0.0001

Data Index: 531357 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.7294. Min Act: -0.0001

Data Index: 340023 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.8262. Min Act: -0.0000

Data Index: 609674 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.7976. Min Act: -0.0001

Data Index: 901115 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.7752. Min Act: -0.0001

Data Index: 297191 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6674. Min Act: -0.0000

Data Index: 361998 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.7106. Min Act: -0.0000

Data Index: 785247 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6307. Min Act: -0.0001

Data Index: 894394 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6941. Min Act: -0.0001

Data Index: 1109719 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1112835 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6619. Min Act: -0.0000

Data Index: 146154 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6494. Min Act: -0.0000

Data Index: 339331 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.5679. Min Act: -0.0000

Data Index: 1147974 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6452. Min Act: -0.0001

Data Index: 115154 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 2.4358. Min Range: -2.4358

Max Act: 1.6627. Min Act: -0.0000

Data Index: 1046253 (C4 (Web Text))

Max Activating Token Index: 793